ME

Mellum2-12B-A2.5B-Instruct

MellumGGUF by MungertUpdated 2026-06-13
Download on Hugging Face
Parameters12.1B
Context128K
Layers28
Architecturemellum
Smallest quant0.0 GB
Quick answer

Mellum2-12B-A2.5B-Instruct needs about 9.2 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 0.0 GB to 24.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Mellum2-12B-A2.5B-Instruct: 12.1B parameter LLM with 2.5B active experts

Mellum2-12B-A2.5B-Instruct is a 12.1B parameter model with a 2.5B active Mixture-of-Experts architecture. It supports a 131,072 token context length and is fine‑tuned for instruction following and tool use.

Good at

  • Instruction following
  • Tool use
  • Low‑latency chat

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is apache-2.0

Best for

  • Interactive chat
  • Code assistance
  • Tool‑enabled workflows

Who it’s for. Developers and researchers needing a responsive instruction‑following model with expert routing. Suitable for local deployment where low latency is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ3_XXS5.6 GB 6.6 GB
Fits Get file →
IQ3_XS5.6 GB 6.6 GB
Fits Get file →
Q3_K_S6.2 GB 7.1 GB
Fits Get file →
IQ3_M6.2 GB 7.2 GB
Fits Get file →
Q3_K_M6.6 GB 7.6 GB
Tight Get file →
IQ4_XS6.7 GB 7.7 GB
Tight Get file →
IQ4_NL6.9 GB 7.8 GB
Tight Get file →
MXFP4_MOE7.0 GB 8.0 GB
Tight Get file →
Q4_07.1 GB 8.0 GB
Too big Get file →
Q4_17.6 GB 8.6 GB
Too big Get file →
Q4_K_S7.7 GB 8.7 GB
Too big Get file →
Q4_K_M8.2 GB 9.2 GB
Too big Get file →
Q5_08.5 GB 9.5 GB
Too big Get file →
Q5_19.3 GB 10.2 GB
Too big Get file →
Q5_K_M9.6 GB 10.5 GB
Too big Get file →
Q6_K_M11.0 GB 12.0 GB
Too big Get file →
Q8_012.9 GB 13.9 GB
Too big Get file →
BF1622.0 GB 23.0 GB
Too big Get file →
F1622.0 GB 23.0 GB
Too big Get file →
BF1624.3 GB 25.3 GB
Too big Get file →

For 8 GB VRAM, use IQ3_XXS or IQ3_XS (≈6.6 GB memory). For 12 GB VRAM, Q4_K_M (≈9.2 GB memory) is a good balance. Higher quants like Q8_0 need 14 GB VRAM or more.

What GPU do you need for Mellum2-12B-A2.5B-Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (7.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_M (11.0 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.9 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (22.0 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (24.3 GB file, about 25.3 GB in use).

Which Mellum2-12B-A2.5B-Instruct quant should you choose?

Q4_K_M is the usual starting point for Mellum2-12B-A2.5B-Instruct: it balances file size and quality well. Here it is a 8.2 GB file.

The Q8_0 file is 12.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemellum
Parameters12.1B (approximate, mixture of experts)
Active parameters2.5B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byMungert
FamilyMellum
Licenseapache-2.0
Downloads (HF)781
Last updated2026-06-13

Frequently asked questions about Mellum2-12B-A2.5B-Instruct

How much VRAM does Mellum2-12B-A2.5B-Instruct need?

About 9.2 GB at Q4_K_M with an 8K context window. That is the 8.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mellum2-12B-A2.5B-Instruct on an 8 GB GPU?

Yes, with Q4_0: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mellum2-12B-A2.5B-Instruct GGUF?

It depends on the quant: file is 0.0 GB, IQ3_XXS is 5.6 GB, IQ3_XS is 5.6 GB, Q3_K_S is 6.2 GB, IQ3_M is 6.2 GB, Q3_K_M is 6.6 GB and 15 more.

What context length does Mellum2-12B-A2.5B-Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Mellum2-12B-A2.5B-Instruct GGUF?

The files are on Hugging Face in the Mungert/Mellum2-12B-A2.5B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mellum2-12B-A2.5B-Instruct use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, using IQ3_XXS or IQ3_XS quantizations which use about 6.6 GB memory at 8k context.

Does the model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mellum models

All Mellum →

Other medium models

All medium models →